R Notebook

library(tidyverse)
library(sf)
library(rmapshaper)
library(here)
library(leaflet)

scotland <- read_sf(here("data_raw/SG_NHS_HealthBoards_2019/SG_NHS_HealthBoards_2019.shp"))

class(scotland)

[1] "sf"         "tbl_df"     "tbl"        "data.frame"

head(scotland, 14)

Simple feature collection with 14 features and 4 fields
Geometry type: MULTIPOLYGON
Dimension:     XY
Bounding box:  xmin: 5512.998 ymin: 530250.8 xmax: 470332 ymax: 1220302
Projected CRS: OSGB 1936 / British National Grid

scotland_geometry <- st_geometry(scotland)

scotland_geometry

Geometry set for 14 features 
Geometry type: MULTIPOLYGON
Dimension:     XY
Bounding box:  xmin: 5512.998 ymin: 530250.8 xmax: 470332 ymax: 1220302
Projected CRS: OSGB 1936 / British National Grid
First 5 geometries:

MULTIPOLYGON (((201916.2 600444.4, 201918.4 600...
MULTIPOLYGON (((345325.9 579663.3, 345325.1 579...
MULTIPOLYGON (((266004.4 543544.6, 266010.9 543...
MULTIPOLYGON (((256533 740502, 256501.5 740379,...
MULTIPOLYGON (((383521.2 771234.7, 383524.3 771...

scotland_simple <- ms_simplify(scotland)

plot(scotland_simple)

alcohol <- read_csv("../data_clean/alcohol.csv") %>% 
  filter(sex == "All") %>% 
  filter(date_code == "2016-2019") %>% 
  filter(alcohol_consumption == "Hazardous/Harmful drinker")

-- Column specification --------------------------------------------------------------------------------------
cols(
  feature_code = col_character(),
  date_code = col_character(),
  measurement = col_character(),
  units = col_character(),
  value = col_double(),
  alcohol_consumption = col_character(),
  sex = col_character(),
  hb_name = col_character()
)

scotland_simple %>% 
  left_join(alcohol, by = c("HBCode" = "feature_code")) %>% 
ggplot() +
  geom_sf(aes(group = hb_name, fill = value)) +
  theme_minimal() +
  theme(panel.grid.major = element_blank(), axis.text = element_blank()) +
  ggtitle("Alcohol Consumption in Scotland") + 
  scale_fill_gradient(low = "green", high = "red")

obesity <- read_csv("../data_clean/obesity.csv") %>% 
  filter(sex == "All") %>% 
  filter(date_code == "2016-2019") %>% 
  filter(obesity == "Obese")

-- Column specification --------------------------------------------------------------------------------------
cols(
  feature_code = col_character(),
  date_code = col_character(),
  measurement = col_character(),
  units = col_character(),
  value = col_double(),
  obesity = col_character(),
  sex = col_character(),
  hb_name = col_character()
)

scotland_simple %>% 
  left_join(obesity, by = c("HBCode" = "feature_code")) %>% 
ggplot() +
  geom_sf(aes(group = hb_name, fill = value)) +
  theme_minimal() +
  theme(panel.grid.major = element_blank(), axis.text = element_blank()) +
  ggtitle("Obesity in Scotland") + 
  scale_fill_gradient(low = "green", high = "red")

smoking_status <- read_csv("../data_clean/smoking_status.csv") %>% 
  filter(sex == "All") %>% 
  filter(date_code == "2016-2019") %>% 
  filter(smoking_status == "Current smoker")

-- Column specification --------------------------------------------------------------------------------------
cols(
  feature_code = col_character(),
  date_code = col_character(),
  measurement = col_character(),
  units = col_character(),
  value = col_double(),
  smoking_status = col_character(),
  sex = col_character(),
  hb_name = col_character()
)

scotland_simple %>% 
  left_join(smoking_status, by = c("HBCode" = "feature_code")) %>% 
ggplot() +
  geom_sf(aes(group = hb_name, fill = value)) +
  theme_minimal() +
  theme(panel.grid.major = element_blank(), axis.text = element_blank()) +
  ggtitle("Smoking Status in Scotland") + 
  scale_fill_gradient(low = "green", high = "red")

e_cig <- read_csv("../data_clean/e_cig.csv") %>% 
  filter(sex == "All") %>% 
  filter(date_code == "2016-2019") %>% 
  filter(e_cigarette_use == "Currently using")

-- Column specification --------------------------------------------------------------------------------------
cols(
  feature_code = col_character(),
  date_code = col_character(),
  measurement = col_character(),
  units = col_character(),
  value = col_double(),
  e_cigarette_use = col_character(),
  sex = col_character(),
  hb_name = col_character()
)

scotland_simple %>% 
  left_join(e_cig, by = c("HBCode" = "feature_code")) %>% 
ggplot() +
  geom_sf(aes(group = hb_name, fill = value)) +
  theme_minimal() +
  theme(panel.grid.major = element_blank(), axis.text = element_blank()) +
  ggtitle("E-cigarette use in Scotland") + 
  scale_fill_gradient(low = "green", high = "red")

obesity_scotland <- read_csv("../data_clean/obesity.csv") %>% 
  filter(sex == "All") %>% 
  filter(hb_name == "Scotland") %>% 
    filter(date_code == "2016-2019") %>% 
  filter(obesity == "Obese")

-- Column specification --------------------------------------------------------------------------------------
cols(
  feature_code = col_character(),
  date_code = col_character(),
  measurement = col_character(),
  units = col_character(),
  value = col_double(),
  obesity = col_character(),
  sex = col_character(),
  hb_name = col_character()
)

alcohol %>%
                    filter(sex == "All" | date_code == "2016-2019") %>%
                    filter(hb_name == "Scotland") %>%
                    filter(alcohol_consumption == "Hazardous/Harmful drinker") %>%
                    select(value) %>%
                    pull()

[1] 24

smoking_status_scotland <- read_csv("../data_clean/smoking_status.csv") %>% 
  filter(sex == "All") %>% 
  filter(hb_name == "Scotland") %>% 
    filter(date_code == "2016-2019") %>% 
  filter(smoking_status == "Current smoker")

-- Column specification --------------------------------------------------------------------------------------
cols(
  feature_code = col_character(),
  date_code = col_character(),
  measurement = col_character(),
  units = col_character(),
  value = col_double(),
  smoking_status = col_character(),
  sex = col_character(),
  hb_name = col_character()
)

smoking_status_scotland

e_cig_scotland <- read_csv("../data_clean/e_cig.csv") %>% 
  filter(sex == "All") %>% 
  filter(hb_name == "Scotland") %>% 
    filter(date_code == "2016-2019") %>% 
  filter(e_cigarette_use == "Currently using")

-- Column specification --------------------------------------------------------------------------------------
cols(
  feature_code = col_character(),
  date_code = col_character(),
  measurement = col_character(),
  units = col_character(),
  value = col_double(),
  e_cigarette_use = col_character(),
  sex = col_character(),
  hb_name = col_character()
)

e_cig_scotland

unique (obesity$sex)

[1] "All"

alcohol %>%
                    filter(sex == "All" | date_code == "2016-2019") %>%
                    filter(hb_name == "Scotland") %>%
                    filter(alcohol_consumption == "Hazardous/Harmful drinker") %>%
                    select(value) %>%
                    pull()

[1] 24